🦖🔍⚙️📸 As an enduring hobby from my childhood, I have collected a plethora of mini-figurines from different brands, limited editions, categories, and themed production lines over the years. Since I was not able to display all of them due to a lack of available space, I had been mulling over cataloging all of my mini-figurines with extensive detail in the form of a web-based application.
Although I am not keen on selling all of my collection, I wanted to enable the application to track eBay and Amazon listings of the target figurines and the adjacent collectibles to get a grasp of the market price and availability of my collection.
1️⃣ Since I did not want to inundate myself with updating listing information manually for each figurine, I decided to employ the @NousResearch #Hermes AI agent to scrape eBay and Amazon listings (with @firecrawl) to conduct extensive market analysis twice every day :) After each analysis, I enabled the Hermes agent to generate a pamphlet (a simple HTML page) for each figurine.
2️⃣ I programmed the web-based mini-figurine cataloger application on @arduino UNO Q via the Arduino App Lab. Since #UNOQ is a compact but extremely powerful development board, I was able to run the Hermes AI agent locally.
3️⃣ Of course, it would not be a worthy mini-figurine cataloger without the feature of automated yet comprehensive figurine photographing :) Thus, I decided to build a rig enabling the App Lab application to capture 360° pictures at varying camera distances automatically. To achieve this automation, I designed a rotary platform swiveling the target mini-figurine and a linear camera slider moving the attached USB camera. The rotary platform is based on a custom worm gear-wheel mechanism, while the camera slider is based on a custom GT2 belt-driven mechanism.
4️⃣ Since I wanted to design a compact rig, I decided to take a different approach to detecting positions and utilized two TCRT5000 infrared (IR) sensor modules. To drive mechanisms, instead of stepper motors, I employed two Pololu micro metal gearmotors due to their small footprint.
5️⃣ To avoid continuing the figurine cataloging procedure once a mini-figurine with an unsteady base falls, I built an @EdgeImpulse audio classification model to detect figurine falls.
6️⃣ To lighten the platform base to emphasize the target figurine details, especially for vintage figurines, I utilized a @seeedstudio WS2813 RGB LED strip. The LED sequence and pixel color can be adjusted manually via buttons or remotely via the RGB color picker wheel presented by the mini-figurine web interface.
7️⃣ As a gimmick, I designed unique magnetic ornaments related to the figurine categories and aesthetic, which can be attached to the rig via the electromagnet :)
➡️ You can inspect the project tutorial on @Hacksterio:
hackster.io/kutluhan-aktar/m…
#Agents #design #edgeAI #AIoT #MachineLearning #Robotics #ArduinoUNOQ #artificialintelligence
